Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 1123
    Prev
    Next
    INDEX
    Explanations

    references to family dynamics and support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    family/household

    np_acts-logits-general · gemini-2.0-flash

    family and household context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ainville
    -0.44
     peer
    -0.40
    petto
    -0.39
    thane
    -0.39
     Peer
    -0.39
     "..\..\..\
    -0.39
    Peer
    -0.39
    leté
    -0.38
     Borne
    -0.38
    errHandler
    -0.38
    POSITIVE LOGITS
     family
    2.62
    family
    2.42
    Family
    2.28
     Family
    2.24
     FAMILY
    2.18
     families
    2.05
     famille
    2.04
    FAMILY
    2.04
     famiglia
    2.02
     familia
    1.96
    Activations Density 0.168%

    No Known Activations